---

DEVLOG #4 (2026-07-01, STAGE 1A PROPOSAL ENGINE)

Project: SL-LLM-R
Tracked Work Time: Not reliably tracked for this entry

Before the update: I lost track of time and forgot to post a devlog. Sorry
about that. I kept working, but I should have documented it properly instead
of reconstructing everything afterwards. I will post devlogs more regularly
from now on.

This session was where the specification first met reality: I built the Stage
1A proposal engine.

The engine takes a ProposalRequest, applies a fixed candidate budget, runs a
configured kernel mixture, and returns a deterministic candidate set. Every
candidate gets a SHA-256 digest, parent reference, depth, and full lineage. No
wall-clock values or floating-point data enter the ID path.

I implemented five proposal kernels:

• Random
• Enumeration
• Mutation
• Combination
• Restart

Budget accounting was more annoying than the algorithms. Rejected and duplicate
candidates still consume budget. That prevents degenerate kernels from running
forever, although it can reduce the effective search budget.

The metrics layer now reports HitRate, diversity, coverage, and novelty. I used
Jaccard distance over intervention fingerprints for the first diversity metric.
It is deterministic, but it may confuse syntactic difference with meaningful
semantic difference.

The Stage 1A schemas include proposal candidates, requests, manifests, split
manifests, decision points, kernel results, and metric reports. Invalid outcomes
use typed reason codes instead of arbitrary strings.

---

What Works

• Deterministic candidate generation under a fixed budget
• Five proposal kernels with traceable lineage
• Reproducible splits and typed validation
• Initial HitRate, diversity, coverage, and novelty metrics

---

Tests

make stage1a-test

The recorded Stage 1A test run passed.

---

Changed Files

Commit: d9f5a10

41 files and about 2,014 added lines.

---

Next Steps

Run the engine against baselines and find out whether it actually does anything
useful.

---

Summary (AI)

The Stage 1A proposal engine is implemented, deterministic, and tested. Its
scientific value is still unknown until baseline evaluation.